Skip to content

GitLab

Commit eec449ca authored by Simon Lui's avatar Simon Lui
Browse files

Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively.

parent 29ccf9f4
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
comfy/model_management.py
View file @ eec449ca
...@@ -488,6 +488,8 @@ def cast_to_device(tensor, device, dtype, copy=False): ...@@ -488,6 +488,8 @@ def cast_to_device(tensor, device, dtype, copy=False):
elif tensor.dtype == torch.bfloat16: elif tensor.dtype == torch.bfloat16:
if hasattr(device, 'type') and device.type.startswith("cuda"): if hasattr(device, 'type') and device.type.startswith("cuda"):
device_supports_cast = True device_supports_cast = True
elif is_intel_xpu():
device_supports_cast = True
if device_supports_cast: if device_supports_cast:
if copy: if copy:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment